Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2356 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.4257. Min Act: -0.1700
Data Index: 3328478 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3768. Min Act: -0.1700
Data Index: 685647 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3440. Min Act: -0.1700
Data Index: 5065072 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2947. Min Act: -0.1700
Data Index: 918662 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2453. Min Act: -0.1700
Data Index: 1569067 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2287. Min Act: -0.1700
Data Index: 685642 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2287. Min Act: -0.1700
Data Index: 685653 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2287. Min Act: -0.1700
Data Index: 8807184 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2287. Min Act: -0.1700
Data Index: 7406888 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2287. Min Act: -0.1700
Data Index: 6280393 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2287. Min Act: -0.1700
Data Index: 5748090 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.1956. Min Act: -0.1700
Data Index: 715439 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2122. Min Act: -0.1700
Data Index: 685651 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2122. Min Act: -0.1700
Data Index: 685643 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2122. Min Act: -0.1700
Data Index: 4541232 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2122. Min Act: -0.1700
Data Index: 4102613 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.1956. Min Act: -0.1700
Data Index: 1524431 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.1956. Min Act: -0.1700
Data Index: 3422699 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.1956. Min Act: -0.1700
Data Index: 398678 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.1956. Min Act: -0.1700
Data Index: 4089902 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19